Accelerated Modeling of Lithium Diffusion in Solid State Electrolytes using Artificial Neural Networks

• Published in: Advanced theory and simulations 2020-09, Vol.3 (9), p.n/a
• Main Authors: Rao, Karun K., Yao, Yan, Grabow, Lars C.
• Format: Article
• Language: English
• Subjects: artificial neural networks; ionic diffusion; machine learning; molecular dynamics; solid state electrolytes
• ISSN: 2513-0390; 2513-0390
• DOI: 10.1002/adts.202000097

Previous efforts to understand structure‐function relationships in high ionic conductivity materials for solid state batteries have predominantly relied on density functional theory (DFT‐) based ab initio molecular dynamics (MD). Such simulations, however, are computationally demanding and cannot be reasonably applied to large systems containing more than a hundred atoms. Here, an artificial neural network (ANN) is trained to accelerate the calculation of high accuracy atomic forces and energies used during such MD simulations. After carefully training a robust ANN for four and five element systems, nearly identical lithium ion diffusivities are obtained for Li10GeP2S12 (LGPS) when benchmarking the ANN‐MD results with DFT‐MD. Applying the ANN‐MD approach, the effect of chlorine doping on the lithium diffusivity is calculated in an LGPS‐like structure and it is found that a dopant concentration of 1.3% maximizes ionic conductivity. The optimal concentration balances the competing consequences of effective atomic radii and dielectric constants on lithium diffusion and agrees with the experimental composition. Performing simulations at the resolution necessary to model experimentally relevant and optimal concentrations would be infeasible with traditional DFT‐MD. Systems that require a large number of simulated atoms can be studied more efficiently while maintaining high accuracy with the proposed ANN‐MD framework. Artificial neural networks (ANN) can replace density functional theory (DFT) as force and energy calculator for molecular dynamics simulations. The ANN provides the accuracy of ab initio techniques while being more computationally efficient. This methodology is used to predict lithium diffusion in Li10GeP2S12 and predicted an ideal chlorine dopant concentration that would be infeasible to model with conventional DFT.